Files

DATA 6de0bf9f5b Initial commit: hardened DeerFlow factory

Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection
hardening:

- New deerflow.security package: content_delimiter, html_cleaner,
  sanitizer (8 layers — invisible chars, control chars, symbols, NFC,
  PUA, tag chars, horizontal whitespace collapse with newline/tab
  preservation, length cap)
- New deerflow.community.searx package: web_search, web_fetch,
  image_search backed by a private SearX instance, every external
  string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>>
  delimiters
- All native community web providers (ddg_search, tavily, exa,
  firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail
  stubs that raise NativeWebToolDisabledError at import time, so a
  misconfigured tool.use path fails loud rather than silently falling
  back to unsanitized output
- Native client back-doors (jina_client.py, infoquest_client.py)
  stubbed too
- Native-tool tests quarantined under tests/_disabled_native/
  (collect_ignore_glob via local conftest.py)
- Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve
  newlines and tabs so list/table structure survives
- Hardened runtime config.yaml references only the searx-backed tools
- Factory overlay (backend/) kept in sync with deer-flow tree as a
  reference / source

See HARDENING.md for the full audit trail and verification steps.

2026-04-12 14:23:57 +02:00

4.3 KiB

Raw Permalink Blame History

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

DeerFlow Frontend is a Next.js 16 web interface for an AI agent system. It communicates with a LangGraph-based backend to provide thread-based AI conversations with streaming responses, artifacts, and a skills/tools system.

Stack: Next.js 16, React 19, TypeScript 5.8, Tailwind CSS 4, pnpm 10.26.2

Commands

Command	Purpose
`pnpm dev`	Dev server with Turbopack (http://localhost:3000)
`pnpm build`	Production build
`pnpm check`	Lint + type check (run before committing)
`pnpm lint`	ESLint only
`pnpm lint:fix`	ESLint with auto-fix
`pnpm typecheck`	TypeScript type check (`tsc --noEmit`)
`pnpm start`	Start production server

No test framework is configured.

Architecture

Frontend (Next.js) ──▶ LangGraph SDK ──▶ LangGraph Backend (lead_agent)
                                              ├── Sub-Agents
                                              └── Tools & Skills

The frontend is a stateful chat application. Users create threads (conversations), send messages, and receive streamed AI responses. The backend orchestrates agents that can produce artifacts (files/code) and todos.

Source Layout (`src/`)

app/ — Next.js App Router. Routes: / (landing), /workspace/chats/[thread_id] (chat).
components/ — React components split into:
- ui/ — Shadcn UI primitives (auto-generated, ESLint-ignored)
- ai-elements/ — Vercel AI SDK elements (auto-generated, ESLint-ignored)
- workspace/ — Chat page components (messages, artifacts, settings)
- landing/ — Landing page sections
core/ — Business logic, the heart of the app:
- threads/ — Thread creation, streaming, state management (hooks + types)
- api/ — LangGraph client singleton
- artifacts/ — Artifact loading and caching
- i18n/ — Internationalization (en-US, zh-CN)
- settings/ — User preferences in localStorage
- memory/ — Persistent user memory system
- skills/ — Skills installation and management
- messages/ — Message processing and transformation
- mcp/ — Model Context Protocol integration
- models/ — TypeScript types and data models
hooks/ — Shared React hooks
lib/ — Utilities (cn() from clsx + tailwind-merge)
server/ — Server-side code (better-auth, not yet active)
styles/ — Global CSS with Tailwind v4 @import syntax and CSS variables for theming

Data Flow

User input → thread hooks (core/threads/hooks.ts) → LangGraph SDK streaming
Stream events update thread state (messages, artifacts, todos)
TanStack Query manages server state; localStorage stores user settings
Components subscribe to thread state and render updates

Key Patterns

Server Components by default, "use client" only for interactive components
Thread hooks (useThreadStream, useSubmitThread, useThreads) are the primary API interface
LangGraph client is a singleton obtained via getAPIClient() in core/api/
Environment validation uses @t3-oss/env-nextjs with Zod schemas (src/env.js). Skip with SKIP_ENV_VALIDATION=1

Code Style

Imports: Enforced ordering (builtin → external → internal → parent → sibling), alphabetized, newlines between groups. Use inline type imports: import { type Foo }.
Unused variables: Prefix with _.
Class names: Use cn() from @/lib/utils for conditional Tailwind classes.
Path alias: @/* maps to src/*.
Components: ui/ and ai-elements/ are generated from registries (Shadcn, MagicUI, React Bits, Vercel AI SDK) — don't manually edit these.

Environment

Backend API URLs are optional; an nginx proxy is used by default:

NEXT_PUBLIC_BACKEND_BASE_URL=http://localhost:8001
NEXT_PUBLIC_LANGGRAPH_BASE_URL=http://localhost:2024

Requires Node.js 22+ and pnpm 10.26.2+.

4.3 KiB Raw Permalink Blame History